We consider an offline learning problem for an agent who first estimates...
While 3D body reconstruction methods have made remarkable progress recen...
We propose a novel framework for solving continuous-time non-Markovian
s...
Millions of smart contracts have been deployed onto Ethereum for providi...
We consider a class of learning problems in which an agent liquidates a ...
We study the global linear convergence of policy gradient (PG) methods f...
APP-installation information is helpful to describe the user's
character...
Building Integrated Photovoltaics (BIPV) is a promising technology to
de...
Despite its popularity in the reinforcement learning community, a provab...
We study finite-time horizon continuous-time linear-convex reinforcement...
The aerodynamic design of modern civil aircraft requires a true sense of...
We analyze the solution regularity and discrete-time approximations of
e...
Fully coupled McKean-Vlasov forward-backward stochastic differential
equ...
Recently, there has been a surge of interest in combining deep learning
...
This paper proposes a relaxed control regularization with general explor...
In this work, we propose a class of numerical schemes for solving semili...
In this paper, we establish that for a wide class of controlled stochast...
Previous approaches for scene text detection usually rely on manually de...